Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures

Danilo Croce, Daniele Rossini, Roberto Basili


Abstract
Nonlinear methods such as deep neural networks achieve state-of-the-art performances in several semantic NLP tasks. However epistemologically transparent decisions are not provided as for the limited interpretability of the underlying acquired neural models. In neural-based semantic inference tasks epistemological transparency corresponds to the ability of tracing back causal connections between the linguistic properties of a input instance and the produced classification output. In this paper, we propose the use of a methodology, called Layerwise Relevance Propagation, over linguistically motivated neural architectures, namely Kernel-based Deep Architectures (KDA), to guide argumentations and explanation inferences. In such a way, each decision provided by a KDA can be linked to real examples, linguistically related to the input instance: these can be used to motivate the network output. Quantitative analysis shows that richer explanations about the semantic and syntagmatic structures of the examples characterize more convincing arguments in two tasks, i.e. question classification and semantic role labeling.
Anthology ID:
W18-5403
Volume:
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Tal Linzen, Grzegorz Chrupała, Afra Alishahi
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16–24
Language:
URL:
https://aclanthology.org/W18-5403
DOI:
10.18653/v1/W18-5403
Bibkey:
Cite (ACL):
Danilo Croce, Daniele Rossini, and Roberto Basili. 2018. Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 16–24, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Explaining non-linear Classifier Decisions within Kernel-based Deep Architectures (Croce et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5403.pdf